# Data-Agnostic Cardinality Learning from Imperfect Workloads

arXiv: https://arxiv.org/abs/2506.16007 · HTML: https://mlsanity.com/paper/2506.16007/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 63 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [MADE: Masked Autoencoder for Distribution Estimation](https://mlsanity.com/paper/1502.03509/) (2015)
- [Learned Cardinalities: Estimating Correlated Joins with Deep Learning](https://mlsanity.com/paper/1809.00677/) (2018)
- [Learning Compositional Representations for Few-Shot Recognition](https://mlsanity.com/paper/1812.09213/) (2018)
- [Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation](https://mlsanity.com/paper/2109.05877/) (2021)
- [Flow-Loss: Learning Cardinality Estimates That Matter](https://mlsanity.com/paper/2101.04964/) (2021)
- [NeuroCard: One Cardinality Estimator for All Tables](https://mlsanity.com/paper/2006.08109/) (2020)
- [A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation](https://mlsanity.com/paper/2107.12295/) (2021)
- [DeepDB: Learn from Data, not from Queries!](https://mlsanity.com/paper/1909.00607/) (2019)
- [FactorJoin: A New Cardinality Estimation Framework for Join Queries](https://mlsanity.com/paper/2212.05526/) (2022)
- [ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads (Extended)](https://mlsanity.com/paper/2310.05349/) (2023)
- [QuickSel: Quick Selectivity Learning with Mixture Models](https://mlsanity.com/paper/1812.10568/) (2018)
- [Duet: efficient and scalable hybriD neUral rElation undersTanding](https://mlsanity.com/paper/2307.13494/) (2023)
- [Convolution and Cross-Correlation of Count Sketches Enables Fast Cardinality Estimation of Multi-Join Queries](https://mlsanity.com/paper/2402.15953/) (2024)
- [A Practical Theory of Generalization in Selectivity Learning](https://mlsanity.com/paper/2409.07014/) (2024)
- [The BigDAWG Polystore System and Architecture](https://mlsanity.com/paper/1609.07548/) (2016)
- [SafeBound: A Practical System for Generating Cardinality Bounds](https://mlsanity.com/paper/2211.09864/) (2022)

## Built on by (most cited first, 1 of 1)

- [TiCard: Deployable EXPLAIN-only Residual Learning for Cardinality Estimation](https://mlsanity.com/paper/2512.14358/) (2025)

## Abstract (arXiv)

Cardinality estimation (CardEst) is a critical aspect of query optimization. Traditionally, it leverages statistics built directly over the data. However, organizational policies (e.g., regulatory compliance) may restrict global data access. Fortunately, query-driven cardinality estimation can learn CardEst models using query workloads. However, existing query-driven models often require access to data or summaries for best performance, and they assume perfect training workloads with complete and balanced join templates (or join graphs). Such assumptions rarely hold in real-world scenarios, in which join templates are incomplete and imbalanced. We present GRASP, a data-agnostic cardinality learning system designed to work under these real-world constraints. GRASP's compositional design generalizes to unseen join templates and is robust to join template imbalance. It also introduces a new per-table CardEst model that handles value distribution shifts for range predicates, and a novel learned count sketch model that captures join correlations across base relations. Across three database instances, we demonstrate that GRASP consistently outperforms existing query-driven models on imperfect workloads, both in terms of estimation accuracy and query latency. Remarkably, GRASP achieves performance comparable to, or even surpassing, traditional approaches built over the underlying data on the complex CEB-IMDb-full benchmark -- despite operating without any data access and using only 10% of all possible join templates.